Juyeob Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Juyeob Lee has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Eunil Park
Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, Republic of Korea and Jaume I University, Castellon, Spain
5 shared publications Donggeun Lee
2 shared publicationsEunil Park
2 shared publicationsChaehee An
1 shared publicationDayeon Han
1 shared publication- Hyeonbin Ji
Sungkyunkwan University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- 6 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Leveraging gated architectures for enhanced long-range dependency learning in non-attributed graphs
- 6 September 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 352
Leveraging gated architectures for enhanced long-range dependency learning in non-attributed graphs
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2486-2495
CLIP-SegFusion: An Attention-Guided Feature Fusion Framework for Multi-Level Detection on AI-Generated Artworks
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2486-2495
Open AccessCLIP-SegFusion: An Attention-Guided Feature Fusion Framework for Multi-Level Detection on AI-Generated Artworks
- 7 June 2026
- Published by Springer Nature
- p. 69-81
Enhancing Graph Neural Networks with Adaptive Relation Learning via Variational Inference
- 7 June 2026
- Published by Springer Nature
- p. 69-81
Enhancing Graph Neural Networks with Adaptive Relation Learning via Variational Inference
- Open Access
- 4 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 84-95
MARs: Multi-Scale Convolution-Attention residual Fusion for Video Summarization
- 4 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 84-95
Open AccessMARs: Multi-Scale Convolution-Attention residual Fusion for Video Summarization
- Open Access
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1234-1236
Revealing Deception through Cognitive Load: A Multimodal Audio-Visual Approach
- 23 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1234-1236
Open AccessRevealing Deception through Cognitive Load: A Multimodal Audio-Visual Approach
- 16 January 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 117
Towards objective heart disease classification: A deep neural network approach for comprehensive diagnosis
- 16 January 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 117
Towards objective heart disease classification: A deep neural network approach for comprehensive diagnosis
- 16 April 2024
- Published by American Physical Society (APS) in Physical Review B
- Vol. 109 (16) , 165130
Solving inverse problems using normalizing flow prior: Application to optical spectra
We introduce a machine learning approach for solving ill-posed inverse problems, specifically addressing the Fredholm integral equation of the first kind. Harnessing the powerful capabilities of normalizing flows to approximate data distributions, combined with a robust probabilistic framework, our approach stands out by delivering robust solutions capable of handling high-level noises and out-of-distribution data and providing uncertainty estimation. A distinct feature lies in the unsupervised learning framework inherent in deep generative models, providing our approach with unparalleled flexibility across diverse experimental setups. This flexibility is exemplified through the successful application of our method to measured optical spectra.
- 16 April 2024
- Published by American Physical Society (APS) in Physical Review B
- Vol. 109 (16) , 165130
Solving inverse problems using normalizing flow prior: Application to optical spectra
We introduce a machine learning approach for solving ill-posed inverse problems, specifically addressing the Fredholm integral equation of the first kind. Harnessing the powerful capabilities of normalizing flows to approximate data distributions, combined with a robust probabilistic framework, our approach stands out by delivering robust solutions capable of handling high-level noises and out-of-distribution data and providing uncertainty estimation. A distinct feature lies in the unsupervised learning framework inherent in deep generative models, providing our approach with unparalleled flexibility across diverse experimental setups. This flexibility is exemplified through the successful application of our method to measured optical spectra.